Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 21146
    Prev
    Next
    INDEX
    Explanations

    the term "consensus" and related discussions of agreement or collective opinion

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    expandindo
    -0.67
    Bly
    -0.58
     Ella
    -0.56
    Jaz
    -0.55
    ly
    -0.55
    |'
    -0.55
    otels
    -0.53
     cucchiaio
    -0.53
    ện
    -0.52
    klo
    -0.50
    POSITIVE LOGITS
     Consensus
    1.72
     consensus
    1.63
    Consensus
    1.53
    consensus
    1.45
     consenso
    1.25
     consens
    1.02
    脚注の使い方
    1.02
     ujednoznacz
    0.93
     CreateTagHelper
    0.93
    ENSUS
    0.88
    Activations Density 0.002%

    No Known Activations